A lower bound on the Bayesian MSE based on the optimal bias function
IEEE Transactions on Information Theory
| Hi-index | 754.90 |
The Weiss-Weinstein bound (WWB) provides a lower limit on the mean-squared error (MSE) achievable by an estimator of an unknown random parameter. In this correspondence, it is shown that some previously proposed simplified versions of the bound do not always hold for constrained parameters, i.e., parameters whose distribution has finite support. These simplifications can produce results which are no longer lower bounds on the MSE. Sufficient conditions are provided for the reductions to be valid.